Sequence mining evolves the preceding concepts even further. This is a process that the data scientist uses to discover a set of patterns that are shared among objects but which also have between them a specific order.
With sequence mining, we acknowledge that there are sequence rules associated with identified sequences. These rules define the pattern's objects and order. A sequence can have multiple rules. The support of a sequence rule can be calculated or determined by the data scientist by the number of sequences containing the rule divided by the total number of sequences. The confidence of a sequence rule will be the number of sequences containing the rule divided by the number of sequences containing its antecedent.
Overall, the objective of sequential rule mining is to discover all sequential rules having a support and confidence no less than two thresholds, given by the user named minsup and minconf.